Image Segmentation and Edge Detection Based on Chan-Vese Algorithm

Nassir Salman

Computer Science Department, Zarqa Private University, Jordan

Abstract: The main idea in this paper is to detect regions (objects) and their boundaries, and to isolate and extract individual components from a medical image. This can be done using K-means firstly to detect regions in a given image. Then based on techniques of curve evolution, Chan-Vese for segmentation and level sets approaches to detect the edges around each selected region. Once we classified our images into different intensity regions based on K-means method, to facilitate separating each region with its boundary and its area individually in the next steps. Then we detect regions whose boundaries are not necessarily defined by gradient using Chan-Vese algorithm for segmentation. In the level set formulation, the problem becomes a mean-curvature flow like evolving the active contour, which will stop on the desired boundary of our selected region which results from K-means step. The final image segmentation results are one closed boundary per actual region  in the image and a segmented map.

Keywords: Chan-Vese approach, K-means, active counters, level set methods, segmentation, edge detection.